Noisy labels are commonly found in real-world data, which cause performance degradation of deep neural networks. Cleaning data manually is labour-intensive and time-consuming. Previous research mostly focuses on enhancing classification models against noisy labels, while the robustness of deep metric learning (DML) against noisy labels remains less well-explored. In this paper, we bridge this important gap by proposing Probabilistic Ranking-based Instance Selection with Memory (PRISM) approach for DML. PRISM calculates the probability of a label being clean, and filters out potentially noisy samples. Specifically, we propose three methods to calculate this probability: 1) Average Similarity Method (AvgSim), which calculates the average similarity between potentially noisy data and clean data; 2) Proxy Similarity Method (ProxySim), which replaces the centers maintained by AvgSim with the proxies trained by proxy-based method; and 3) von Mises-Fisher Distribution Similarity (vMF-Sim), which estimates a von Mises-Fisher distribution for each data class. With such a design, the proposed approach can deal with challenging DML situations in which the majority of the samples are noisy. Extensive experiments on both synthetic and real-world noisy dataset show that the proposed approach achieves up to 8.37% higher Precision@1 compared with the best performing state-of-the-art baseline approaches, within reasonable training time.
翻译:在现实世界数据中通常会发现噪音标签,这导致深神经网络的性能退化。人工清洗数据是劳动密集型和耗时的。以往的研究主要侧重于加强针对噪音标签的分类模型,而针对噪音标签的深度衡量学习(DML)的稳健性仍然不太受到很好探讨。在本文中,我们通过提议DML(PRISM)采用基于记忆(PRISM)的概率分级选择程序(PRISM)方法来弥补这一重要差距。 PRISM计算标签清洁的可能性,并过滤可能很吵的样本。具体地说,我们提出了三种方法来计算这一概率:(1) 平均相似性方法(AvgSim),该方法计算出潜在噪音数据与清洁数据之间的平均相似性模式;(2) 代之为AvgSim(ProxySim)所维持的中心,代之以代之以代用基于代用方法(PRISMM)的准度;(3) von Mis-Fis-Fisher 分布相似性(VMF-Sim),该方法估算出每类数据流出一个可能很吵的样本分布。我们提出了三种方法来计算这一方法来计算这一方法。我们提出了每类数据测测测测算出每类数据分布的频率的分布的分布的分布的分布的分布。在这种方法,在这种方法在设计中,在最高级的模型中,在最高级的模型中,在最高级的模型中,在设计和最高级方法在最高级的模型中,在最高级的模型中,在最高级的模拟式的模型中,在最高级的模拟的模拟的模拟的模拟的模拟的模拟的模拟的模拟的模拟的模拟的模拟的模拟的模拟的模拟的模拟方法与最接近性方法与最接近性方法在最接近性方法与最接近性方法在进行。